Scaling over Space: Advancing the Model and Data Foundations of GeoAI Advances in deep learning and foundation models are raising expectations for general-purpose learning and creating new opportunities to harness the geospatial data revolution for Earth monitoring and scientific discovery, with broad benefits for agriculture, energy, water, transportation, smart cities, and disaster response. At the same time, major challenges remain for large-scale geospatial applications, including spatial variability that substantially weakens model generalization, limited and localized training data, and high computational demands that constrain and slow scientific discovery. This talk will discuss both AI model and data foundations for scaling geospatial applications, including geo-aware learning, knowledge-guided learning, task-aligned pretraining, and new benchmark datasets.
Bio: Yiqun Xie is an Assistant Professor in the Center for Geospatial Information Science, Dept. of Geographical Sciences, and an Affiliate Faculty at the AI Interdisciplinary Institute at Maryland (AIM), at the University of Maryland. He received his PhD in Computer Science at the University of Minnesota, and his research addresses fundamental challenges facing AI for spatio-temporal data and scientific problems. His work focuses on advancing use-inspired AI models with explicit geo-awareness and knowledge-guidance to improve model generalizability for large-scale applications and accelerate scientific discoveries. He is leading multiple interdisciplinary AI projects funded by NSF, NASA, and Google, with research published in both top AI and domain science venues. His work has been recognized by multiple best paper awards from IEEE ICDM 2021, ACM SIGSPATIAL 2025 and 2019, SIAM Data Mining 2023, SSTD 2019, and was highlighted by the Great Innovative Ideas program by CCC at CRA. He delivered invited panel talks on GeoAI for committee meetings of the National Academies on Science, Engineering, and Medicine (NASEM) and the National Geospatial Advisory Committee (NGAC).
